© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64595
    Prev
    Next
    INDEX
    Explanations

    hot and common pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    has
    -0.82
    ed
    -0.77
    ステル
    -0.76
    ooh
    -0.74
    edx
    -0.74
     swirl
    -0.73
    inv
    -0.72
    are
    -0.71
     carte
    -0.71
    ep
    -0.70
    POSITIVE LOGITS
     hot
    1.98
    Hot
    1.89
     Hot
    1.77
     🔥
    1.59
    hot
    1.56
     HOT
    1.54
     hotter
    1.52
    🔥
    1.39
    shot
    1.32
     hottest
    1.23
    Activations Density 0.019%

    No Known Activations